Update pep8 (#78)

* simplify requirements file

* style

* apply linter

ch04/01_main-chapter-code/previous_chapters.py

@@ -27,7 +27,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -49,7 +49,7 @@ class MultiHeadAttention(nn.Module):
 
         self.d_out = d_out
         self.num_heads = num_heads
-        self.head_dim = d_out // num_heads # Reduce the projection dim to match desired output dim
+        self.head_dim = d_out // num_heads  # Reduce the projection dim to match desired output dim
 
         self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
         self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
@@ -61,13 +61,13 @@ class MultiHeadAttention(nn.Module):
     def forward(self, x):
         b, num_tokens, d_in = x.shape
 
-        keys = self.W_key(x) # Shape: (b, num_tokens, d_out)
+        keys = self.W_key(x)  # Shape: (b, num_tokens, d_out)
         queries = self.W_query(x)
         values = self.W_value(x)
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 
@@ -84,15 +84,15 @@ class MultiHeadAttention(nn.Module):
 
         # Use the mask to fill attention scores
         attn_scores.masked_fill_(mask_bool, -torch.inf)
-        
+
         attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
         attn_weights = self.dropout(attn_weights)
 
         # Shape: (b, num_tokens, num_heads, head_dim)
-        context_vec = (attn_weights @ values).transpose(1, 2) 
-        
+        context_vec = (attn_weights @ values).transpose(1, 2)
+
         # Combine heads, where self.d_out = self.num_heads * self.head_dim
         context_vec = context_vec.contiguous().view(b, num_tokens, self.d_out)
-        context_vec = self.out_proj(context_vec) # optional projection
+        context_vec = self.out_proj(context_vec)  # optional projection
 
-        return context_vec
+        return context_vec